Huggin Fork

huginnfork's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in huginnfork/Qwen3.8-27B-FP8 11 days ago

vllm: Vision Model missing warning

3

#5 opened 11 days ago by

peterdab

New activity in huginnfork/Qwen3.8-27B-NVFP4A16 14 days ago

Will there be a GGUF version of the model?

1

#3 opened 15 days ago by

Siri0s

New activity in huginnfork/Qwen3.8-27B-NVFP4A16 15 days ago

Does not work with vllm 0.27.1

1

#2 opened 15 days ago by

flaviusburca

updated a collection 15 days ago

Qwen3.8-27B

Collection

FP8 & NVFP4 quants of Qwen/Qwen3.8-27B. Reserved ahead of the upstream release — weights land as soon as the base model ships. • 4 items • Updated 15 days ago • 16

New activity in huginnfork/Qwen3.8-27B-FP8 15 days ago

Slower than bf16 on DGX Spark

1

#4 opened 15 days ago by

TeAmErX

liked 2 models 15 days ago

huginnfork/Qwen3.8-27B-NVFP4A16

Image-Text-to-Text • 28B • Updated 16 days ago • 7.22k • 20

huginnfork/Qwen3.8-27B-FP8

Image-Text-to-Text • 28B • Updated 16 days ago • 8.66k • 37

updated 2 models 16 days ago

huginnfork/Qwen3.8-27B-NVFP4A16

Image-Text-to-Text • 28B • Updated 16 days ago • 7.22k • 20

huginnfork/Qwen3.8-27B-FP8

Image-Text-to-Text • 28B • Updated 16 days ago • 8.66k • 37

New activity in huginnfork/Qwen3.8-27B-FP8 17 days ago

Nice mockery from QWEN team they release the 2.4T model nobody can use but the 27B is 2 days delayed. WTF

4

#2 opened 18 days ago by

akierum

🚩 Report: Spam

👍 1

1

#3 opened 17 days ago by

Voidreaper2026

upvoted a collection 18 days ago

Qwen3.8-27B

Collection

FP8 & NVFP4 quants of Qwen/Qwen3.8-27B. Reserved ahead of the upstream release — weights land as soon as the base model ships. • 4 items • Updated 15 days ago • 16

New activity in huginnfork/Qwen3.8-27B-FP8 19 days ago

nothingburger

👍 4

4

#1 opened 20 days ago by

wijjjj

updated 3 collections 21 days ago

Qwen3.8-27B

Collection

FP8 & NVFP4 quants of Qwen/Qwen3.8-27B. Reserved ahead of the upstream release — weights land as soon as the base model ships. • 4 items • Updated 15 days ago • 16

Ornith-1.0-35B

Collection

FP8 & NVFP4 quants of the 256-expert Ornith-1.0-35B MoE. Routers, SSM block and vision tower stay bf16. Serve in vLLM or SGLang. • 2 items • Updated 21 days ago

Tess-4-27B

Collection

FP8 & NVFP4 quants of migtissera/Tess-4-27B, a Qwen3.6-27B reasoning fine-tune. KLD is measured against bf16 Tess, so it isolates quant loss. • 2 items • Updated 21 days ago